I will ai quantitative trading bot

This project delivers a custom AI trading system built using TensorFlow, OpenAI Gymnasium, custom RL, and LSTM-based recurrent architectures, specifically designed for financial time-series learning under any noisy and biased market conditions, accurate regime detection during training.

The core focus of this work is reducing policy bias, improving directional accuracy, and stabilizing learning in environments where most trading agents fail.

Key outcomes from this approach include:

Designing near-unbiased PPO agents even when trained on heavily skewed market data

Reducing sensitivity to short-term price noise that typically causes agents to lock capital in the wrong direction

Achieving stable training without reward clipping or information loss

Handling non-stationary market data using custom PPO & recurrent (LSTM-based) policies.